Body Weight Estimation in Holstein × Zebu Crossbred Heifers: Comparative Analysis of XGBoost and LightGBM Algorithms

ABSTRACT This study evaluates the effectiveness of XGBoost and LightGBM algorithms for estimating the live weight of Holstein×Zebu crossbred heifers. The study compares the performance of both algorithms using a wide range of biometric measurements and tests various hyperparameter settings. The rese...

Full description

Saved in:
Bibliographic Details
Main Authors: Jose Herrera‐Camacho, Cem Tırınk, Rosa Inés Parra‐Cortés, Lütfi Bayyurt, Rashit Uskenov, Karlygash Omarova, Aizhan Makhanbetova, Kadyrbai Chekirov, Alfonso Juventino Chay‐Canul
Format: Article
Language:English
Published: Wiley 2025-07-01
Series:Veterinary Medicine and Science
Subjects:
Online Access:https://doi.org/10.1002/vms3.70422
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849303994293288960
author Jose Herrera‐Camacho
Cem Tırınk
Rosa Inés Parra‐Cortés
Lütfi Bayyurt
Rashit Uskenov
Karlygash Omarova
Aizhan Makhanbetova
Kadyrbai Chekirov
Alfonso Juventino Chay‐Canul
author_facet Jose Herrera‐Camacho
Cem Tırınk
Rosa Inés Parra‐Cortés
Lütfi Bayyurt
Rashit Uskenov
Karlygash Omarova
Aizhan Makhanbetova
Kadyrbai Chekirov
Alfonso Juventino Chay‐Canul
author_sort Jose Herrera‐Camacho
collection DOAJ
description ABSTRACT This study evaluates the effectiveness of XGBoost and LightGBM algorithms for estimating the live weight of Holstein×Zebu crossbred heifers. The study compares the performance of both algorithms using a wide range of biometric measurements and tests various hyperparameter settings. The research results show that the XGBoost algorithm provides almost perfect agreement with an R2 value of 0.999 on the training set and high performance with an R2 value of 0.986 on the test set. The LightGBM algorithm also achieved effective results with R2 values of 0.986 and 0.981 on both training and test sets. The machine learning algorithms used in the current study stand out as having the potential to provide a practical and economical solution for live weight estimation in livestock enterprises and especially for herd management applications in rural areas through input variables such as body measurements, milk yield, etc. However, the obtained results in the current study reveal the potential of machine learning algorithms for live weight estimation in the livestock sector and indicate that advanced research is needed for the optimisation of these algorithms.
format Article
id doaj-art-e69f402f6e1f4ffda07f6c31ac8e98ef
institution Kabale University
issn 2053-1095
language English
publishDate 2025-07-01
publisher Wiley
record_format Article
series Veterinary Medicine and Science
spelling doaj-art-e69f402f6e1f4ffda07f6c31ac8e98ef2025-08-20T03:55:53ZengWileyVeterinary Medicine and Science2053-10952025-07-01114n/an/a10.1002/vms3.70422Body Weight Estimation in Holstein × Zebu Crossbred Heifers: Comparative Analysis of XGBoost and LightGBM AlgorithmsJose Herrera‐Camacho0Cem Tırınk1Rosa Inés Parra‐Cortés2Lütfi Bayyurt3Rashit Uskenov4Karlygash Omarova5Aizhan Makhanbetova6Kadyrbai Chekirov7Alfonso Juventino Chay‐Canul8Universidad Michoacana de San Nicolás de Hidalgo Morelia Michoacán MexicoDepartment of Animal Science Igdir University, Faculty of Agriculture Iğdır TürkiyeUniversidad de Ciencias Aplicadas y Ambientales U.D.C.A, Área de Ciencias Agropecuarias, Grupo de Investigación en Ciencia Animal Bogotá ColombiaFaculty of Agriculture Department of Animal Science Tokat Gaziosmanpaşa University Tokat TürkiyeAgronomic Faculty Saken Seifullin Kazakh Agrotechnical University Astana KazakhstanFaculty of Veterinary and Livestock Technology Saken Seifullin Kazakh Agrotechnical University Astana KazakhstanFaculty of Veterinary and Livestock Technology Saken Seifullin Kazakh Agrotechnical University Astana KazakhstanKyrgyz‐Turkish Manas University Bishkek Kyrgyz RepublicDivisión Académica de Ciencias Agropecuarias Universidad Juárez Autónoma de Tabasco Villahermosa Tabasco MéxicoABSTRACT This study evaluates the effectiveness of XGBoost and LightGBM algorithms for estimating the live weight of Holstein×Zebu crossbred heifers. The study compares the performance of both algorithms using a wide range of biometric measurements and tests various hyperparameter settings. The research results show that the XGBoost algorithm provides almost perfect agreement with an R2 value of 0.999 on the training set and high performance with an R2 value of 0.986 on the test set. The LightGBM algorithm also achieved effective results with R2 values of 0.986 and 0.981 on both training and test sets. The machine learning algorithms used in the current study stand out as having the potential to provide a practical and economical solution for live weight estimation in livestock enterprises and especially for herd management applications in rural areas through input variables such as body measurements, milk yield, etc. However, the obtained results in the current study reveal the potential of machine learning algorithms for live weight estimation in the livestock sector and indicate that advanced research is needed for the optimisation of these algorithms.https://doi.org/10.1002/vms3.70422body weight predictioncrossbred heiferLightGBMmachine learningXGBoost
spellingShingle Jose Herrera‐Camacho
Cem Tırınk
Rosa Inés Parra‐Cortés
Lütfi Bayyurt
Rashit Uskenov
Karlygash Omarova
Aizhan Makhanbetova
Kadyrbai Chekirov
Alfonso Juventino Chay‐Canul
Body Weight Estimation in Holstein × Zebu Crossbred Heifers: Comparative Analysis of XGBoost and LightGBM Algorithms
Veterinary Medicine and Science
body weight prediction
crossbred heifer
LightGBM
machine learning
XGBoost
title Body Weight Estimation in Holstein × Zebu Crossbred Heifers: Comparative Analysis of XGBoost and LightGBM Algorithms
title_full Body Weight Estimation in Holstein × Zebu Crossbred Heifers: Comparative Analysis of XGBoost and LightGBM Algorithms
title_fullStr Body Weight Estimation in Holstein × Zebu Crossbred Heifers: Comparative Analysis of XGBoost and LightGBM Algorithms
title_full_unstemmed Body Weight Estimation in Holstein × Zebu Crossbred Heifers: Comparative Analysis of XGBoost and LightGBM Algorithms
title_short Body Weight Estimation in Holstein × Zebu Crossbred Heifers: Comparative Analysis of XGBoost and LightGBM Algorithms
title_sort body weight estimation in holstein zebu crossbred heifers comparative analysis of xgboost and lightgbm algorithms
topic body weight prediction
crossbred heifer
LightGBM
machine learning
XGBoost
url https://doi.org/10.1002/vms3.70422
work_keys_str_mv AT joseherreracamacho bodyweightestimationinholsteinzebucrossbredheiferscomparativeanalysisofxgboostandlightgbmalgorithms
AT cemtırınk bodyweightestimationinholsteinzebucrossbredheiferscomparativeanalysisofxgboostandlightgbmalgorithms
AT rosainesparracortes bodyweightestimationinholsteinzebucrossbredheiferscomparativeanalysisofxgboostandlightgbmalgorithms
AT lutfibayyurt bodyweightestimationinholsteinzebucrossbredheiferscomparativeanalysisofxgboostandlightgbmalgorithms
AT rashituskenov bodyweightestimationinholsteinzebucrossbredheiferscomparativeanalysisofxgboostandlightgbmalgorithms
AT karlygashomarova bodyweightestimationinholsteinzebucrossbredheiferscomparativeanalysisofxgboostandlightgbmalgorithms
AT aizhanmakhanbetova bodyweightestimationinholsteinzebucrossbredheiferscomparativeanalysisofxgboostandlightgbmalgorithms
AT kadyrbaichekirov bodyweightestimationinholsteinzebucrossbredheiferscomparativeanalysisofxgboostandlightgbmalgorithms
AT alfonsojuventinochaycanul bodyweightestimationinholsteinzebucrossbredheiferscomparativeanalysisofxgboostandlightgbmalgorithms